This paper examines how people communicate with computers using speech. Automatic
speech recognition (ASR) transforms speech into text, while automatic speech synthesis [or …

We present in this paper a statistical model for languageindependent bi-directional
conversion between spelling and pronunciation, based on joint grapheme/phoneme units1 …

Requirements engineering heavily relies on oral and informal communication like meetings,
phone calls, and e-mails. Some requirements are traditionally communicated outside formal …

Interactive spoken dialog provides many new challenges for natural language
understanding systems. One of the most critical challenges is simply determining the …

Abstract Language models for speech recognition concen-Irate solely on recognizing the
words that were spoken. In this paper, we advocate redefining the speech recognition …

This paper describes a new kind of language models composed of several local models and
a general model linking the local models together. Local models describe more finely …

The main goal of the present work is to explore the use of rich lexical information in
language modelling. We reformulated the task of a language model from predicting the next …

A popular heuristic technique for pronunciation modelling extends the lexicon with
pronunciations for selected word phrases or multiword units in order to capture limited cross …

We consider phrase based Language Models (LM), which generalize the commonly used
word level models. Similar concept on phrase based LMs appears in speech recognition …

Language model is one of the most important modules in statistical machine translation and
currently the word-based language model dominants this community. However, many …